Research and application of association rule algorithm and an optimized grey model in carbon emissions forecasting

Accurate carbon emissions forecasting plays a pivotal role in reducing global warming by providing references to formulate emission reduction policies. Although numerous studies have focused on forecasting China's carbon emissions, the results of different methods are contradicting, because they are based on different data and use different parameters. This paper aims to propose a hybrid carbon emissions forecasting model based on multi-factor identification to offer reliable forecasting results. First, association rule algorithm was applied to find influencing factors and analyse their joint effects on carbon emissions from the perspective of time and space. Energy consumption, economic growth, industrial structure, foreign direct investment, and urbanization are proven to be the five major factors that can cause an increase in carbon emissions. Second, a multivariate grey model optimized by firefly algorithm was utilized to conduct carbon emissions forecasting under different scenarios. Empirical results indicated that the proposed hybrid model had the best performance compared to other methods. If no effective measures are taken, it is difficult for China to realize its goal for carbon emissions reduction in 2020.